CN110681097B - Full-intelligent fire extinguishing system - Google Patents
Full-intelligent fire extinguishing system Download PDFInfo
- Publication number
- CN110681097B CN110681097B CN201910945263.2A CN201910945263A CN110681097B CN 110681097 B CN110681097 B CN 110681097B CN 201910945263 A CN201910945263 A CN 201910945263A CN 110681097 B CN110681097 B CN 110681097B
- Authority
- CN
- China
- Prior art keywords
- module
- fire
- algorithm module
- information
- algorithm
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 139
- 238000004891 communication Methods 0.000 claims abstract description 27
- 238000004458 analytical method Methods 0.000 claims description 58
- 238000000034 method Methods 0.000 claims description 38
- 239000011159 matrix material Substances 0.000 claims description 29
- 238000005070 sampling Methods 0.000 claims description 26
- 238000012544 monitoring process Methods 0.000 claims description 25
- 230000008859 change Effects 0.000 claims description 18
- 230000008569 process Effects 0.000 claims description 18
- 238000001914 filtration Methods 0.000 claims description 12
- 230000010354 integration Effects 0.000 claims description 11
- 230000033001 locomotion Effects 0.000 claims description 8
- 239000000463 material Substances 0.000 claims description 8
- 206010000369 Accident Diseases 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 5
- 230000035772 mutation Effects 0.000 claims description 5
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000010191 image analysis Methods 0.000 claims description 3
- 238000005507 spraying Methods 0.000 claims description 3
- 238000001931 thermography Methods 0.000 claims description 3
- 238000003672 processing method Methods 0.000 claims 2
- 239000000126 substance Substances 0.000 claims 1
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000012706 support-vector machine Methods 0.000 description 4
- 239000000779 smoke Substances 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000006698 induction Effects 0.000 description 2
- 238000012567 pattern recognition method Methods 0.000 description 2
- 230000001629 suppression Effects 0.000 description 2
- 230000003111 delayed effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007480 spreading Effects 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A62—LIFE-SAVING; FIRE-FIGHTING
- A62C—FIRE-FIGHTING
- A62C37/00—Control of fire-fighting equipment
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/12—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions
- G08B17/125—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions by using a video camera to detect fire or smoke
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B29/00—Checking or monitoring of signalling or alarm systems; Prevention or correction of operating errors, e.g. preventing unauthorised operation
- G08B29/18—Prevention or correction of operating errors
- G08B29/185—Signal analysis techniques for reducing or preventing false alarms or for enhancing the reliability of the system
Landscapes
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Public Health (AREA)
- Computer Security & Cryptography (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Fire-Detection Mechanisms (AREA)
- Alarm Systems (AREA)
- Closed-Circuit Television Systems (AREA)
- Fire Alarms (AREA)
Abstract
The invention discloses a full-intelligent fire extinguishing system which comprises a thermal imager module, a digital signal processing module, an algorithm module 1, a mode generating module, a fire fighting gun pump, a cloud deck, an image acquisition module, a storage module, an algorithm module 2, a control module and a communication module. The fully-intelligent fire extinguishing system can realize fire early warning, find fire intelligent decision, filter false alarm and autonomously decide the optimal fire extinguishing scheme, and has the beneficial effects of all-weather and fully-intelligent handling of the fire hazard at a target point and fire extinguishing handling.
Description
Technical Field
The invention belongs to the field of public safety, and particularly relates to a full-intelligent fire extinguishing system.
Background
At present, in order to reduce the damage and loss of a major fire-fighting hazard source when a fire disaster happens, the fire-fighting system is provided with special fire-fighting systems, and the fire-fighting systems can realize smoke induction and temperature induction so as to spread fire extinguishing at the first time when the fire occurs and prevent the fire from spreading. Such fire suppression systems have good automation capabilities, but have limited utility in open air and are subject to false alarms. The relatively advanced automatic fire extinguishing system is provided with the thermal imager, and the problems of monitoring and sensing of fire conditions in open-air occasions are solved, however, the fire extinguishing system lacks the autonomous decision-making capability and does not solve the problem of misinformation, a specially-assigned person is still required to be monitored on duty for 24 hours, and the final decision-making needs to be solved by manpower, so that the optimal disposal time is delayed.
Disclosure of Invention
The invention aims to provide a full-intelligent fire extinguishing system, which realizes fire early warning, finds intelligent fire decision, filters false alarms and autonomously decides an optimal fire extinguishing scheme, and has the effects of all-weather and full-intelligent handling of fire hazards at a target point and fire extinguishing.
The specific technical scheme is as follows:
the full intelligent fire extinguishing system comprises:
the system comprises a thermal imager module, a digital signal processing module, an algorithm module 1, a mode generating module, a fire gun pump, a holder, an image acquisition module, a storage module, an algorithm module 2, a control module and a communication module.
The thermal imager module is used for monitoring thermal imaging information of the fire-fighting hazard source in real time to obtain two-dimensional temperature distribution information of the fire-fighting hazard source equipment and the material surface, outputting a full-color image in an RGB (red, green and blue) mode by combining the temperature distribution information, as shown in FIG. 2, and sending the two-dimensional temperature distribution information to the digital signal processing module. The thermal imager module has the advantages of all-weather monitoring, and no influence of smoke shielding and severe weather.
The digital signal processing module is used for receiving the two-dimensional temperature distribution information of the fire-fighting hazard source equipment and the material surface, which is transmitted by the thermal imager module, performing digital characteristic processing on the two-dimensional temperature distribution information and transmitting the processed information to the algorithm module 1, so that the algorithm module 1 can directly analyze the temperature information.
Further, the process of the digital signal processing module performing digital feature processing on the two-dimensional temperature distribution information refers to fig. 3:
s201, storing two-dimensional temperature distribution information to a matrix TP by using description relative to a Cartesian coordinate systemM×N×4Wherein, M and N represent the number of pixels of the two-dimensional temperature distribution full-color image, and dimension 4 represents the information contained in one pixel, including the RGB value and the temperature value corresponding to the RGB value.
Then there is a change in the number of,
wherein (R)ij,Gij,Bij,tij)ijRGB value and temperature value representing the (i, j) th pixel, i ∈ [0, (M-1)],j∈[0,(N-1)].
S202 traverse matrix TPM×N×4Extracting pixel information exceeding a temperature threshold value therefrom;
the temperature threshold is manually set, and is marked as omega to indicate that the normal temperature is exceeded, and a limit value which needs extra attention can be set as a minimum threshold value 200 ℃ of the ignition point of a general material in actual operation.
Extraction of TPM×N×4Middle temperature value tijThe elements larger than omega form a new matrix TNm×n×4Then there is
Wherein (R)uv,Guv,Buv,tuv)uvRGB value and temperature value representing the (u, v) th pixel, u belongs to [0, (m-1)],v∈[0,(n-1)]And t isuv>ω.
S203 adopts a fixed window method to carry out over-temperature threshold matrix TNm×n×4Filtering, and obtaining the overtemperature threshold matrix TN 'after filtering'm×n×4To the algorithm module 1.
For TNm×n×4All elements (R) in the matrixuv,Guv,Buv,tuv)uvFiltering by using a fixed window method in sequence, wherein the fixed window method is that a window with a fixed pixel size is adopted, and the window size of the fixed pixel should be as small as possible;
obtaining a final over-temperature threshold matrix recorded as TN 'after filtering treatment by a fixed window method'p×q×4(p is less than or equal to m, q is less than or equal to n) and TN'p×q×4To the algorithm module 1.
The algorithm module 1 is stored with a computer program, and is used for receiving the temperature information transmitted by the digital signal processing module, analyzing and judging the fire hazard and the fire occurrence event according to the received temperature information, and transmitting the analysis and judgment result to the control module.
Further, the algorithm module 1 analyzes the temperature information to determine the processing procedure of the fire hazard and the fire occurrence event, referring to fig. 4:
s301, receiving two-dimensional temperature distribution information transmitted by the digital signal processing module, and performing integration processing on an over-temperature threshold region to obtain an integrated attention object;
the algorithm module 1 receives two-dimensional temperature distribution information transmitted by the digital signal processing module, wherein the two-dimensional temperature distribution information is an over-temperature threshold matrix TN'p×q×4From TN'p×q×4And (4) whether the pixel coordinates of the middle element are continuous or not is carried out to carry out integration processing. Specifically, assuming that the coordinates of the pixel a are (i, j), the coordinates of the pixel B are (i +1, j), the coordinates of the pixel C are (i, j +1), and the coordinates of the pixel D are (i +1, j +1), the pixels A, B, C, D are two-by-two consecutive.
After integration treatment, original overtemperature threshold matrix TN'p×q×4Will be divided into several sub-matrices, denoted as (TN')1...(TN′)wWherein w represents the original overtemperature threshold matrix TN 'after adopting the integration treatment'p×q×4The number of sub-matrices divided, thus resulting in w integrated objects of interest.
S302, the pixel area of the attention object and the increment of the characteristic temperature are calculated, and the fire hazard and the fire occurrence event are judged according to the increment.
(1) For the integrated w objects of interest (TN')1...(TN′)wThe pixel area of each object of interest is calculated separately.
The pixel area is used to describe the pixel size of the object of interest, and the pixel area of the object of interest can be used as the object of interest (TN')iSo that the pixel area of the object of interest is equal to the sum of the pixels represented by the elements in the object of interest:
wherein SiA pixel area representing an ith object of interest; p is a radical ofiRepresenting an object of interest (TN')iThe number of rows of middle elements; q. q.siRepresenting an object of interest (TN')iThe number of columns of medium elements.
(2) For the integrated w objects of interest (TN')1...(TN′)wThe characteristic temperature of each object of interest is calculated separately.
The characteristic temperature is used to characterize the proportion of the highest temperature in a certain object of interest. Object of interest (TN')iThe characteristic temperature calculation method is as follows:
wherein, tfiRepresenting an object of interest (TN')iThe characteristic temperature of (a); p is a radical ofiRepresenting an object of interest (TN')iThe number of rows of middle elements; q. q.siRepresenting an object of interest (TN')iThe number of columns of medium elements; cmiIndicates that t is reachedmiThe number of pixels of (a); t is tmiRepresenting an object of interest (TN')iThe maximum value of the temperature of each pixel in the array.
(3) Calculating the increment of the pixel area and the characteristic temperature, and judging the fire hazard and the fire occurrence event according to the increment, wherein the processing process comprises the following steps:
calculating pixel area growth ga:
Wherein tau isoRepresenting the temperature sampling period of the system thermal image; s'iPixel area, S, representing the current sampling periodiRepresenting the pixel area of the previous sampling period.
② calculating characteristic temperature growth gt:
Wherein, t'fiA characteristic temperature representing a current sampling period; t is tfiRepresenting the characteristic temperature of the previous sampling period.
Analyzing area growth and characteristic temperature growth data of a plurality of continuous sampling periods, and judging the processing process of fire hazard and fire incident:
respectively, representing characteristic temperature growth data for successive r sampling periods.
if it isIllustrating a sharp rise in the characteristic temperature of the object of interest over time;
the mode generating module is used for receiving the instruction information transmitted by the control module, generating corresponding working mode information according to the instruction information and then transmitting the working mode information to the fire-fighting gun pump.
Further, the processing procedure of the mode generation module generating the corresponding working mode according to the instruction information refers to fig. 5:
s401, receiving a working mode control instruction transmitted by a control module, and analyzing the control instruction into a PWM (pulse width modulation) signal;
the working mode instruction transmitted by the control module comprises an event decision result and pixel area growth and characteristic temperature growth data of an object of interest in the latest sampling period, and the mode generation module analyzes the working mode instruction into a PWM (pulse width modulation) signal by adopting the following formula after receiving the working mode instruction:
wherein D isjPWM duty cycle representing generating mode of operation
S402, sending the working mode information to the fire fighting gun pump in a PWM signal mode, and controlling the fire fighting gun pump to work according to a specified mode.
The fire gun pump is used for receiving the working mode information sent by the mode generating module and entering a corresponding working mode so as to control the fire gun to carry out fire extinguishing treatment more efficiently.
The fire-fighting gun holder is provided with a fire-fighting gun for controlling the spraying angle and direction of the fire-fighting gun.
The image acquisition module is used for acquiring field video monitoring data and storing the image information into the storage module.
And the storage module is used for storing the field video monitoring data transmitted by the image acquisition module.
The algorithm module 2 is stored with a computer program and is used for analyzing the video monitoring data in the storage module in real time so as to automatically judge whether open fire occurs on the site and send the judgment result to the control module.
The algorithm module 2 analyzes the video monitoring data in real time to automatically judge whether open fire occurs on the site.
Further, the naked light is analyzed and judged in real time according to video monitoring data, an open light pattern recognition method based on OpenCV is adopted, the OpenCV is an open-source cross-platform computer vision library, an SVM (support vector machine) classifier, a decision tree classifier and an Adaboost (adaptive enhancement) classifier are adopted to judge the naked light in a mixed mode based on the OpenCV, and a person skilled in the art can refer to the prior art, and detailed steps of the method are not specifically limited.
The control module is mainly used for data transmission and control of the whole fire extinguishing system, and specifically has the following functions:
(1) receiving the analysis and judgment results of the fire hazard and the fire incident from the algorithm module 1, calling a video analysis result from the algorithm module 2 according to the analysis and judgment results, and making a final control decision;
(2) receiving a video analysis result transmitted by the algorithm module 2, calling a thermal image temperature information analysis result from the algorithm module 1 according to the result, and making a final control decision;
(3) reading data from the storage module and the algorithm module 1, and sending the data to a third-party system through a communication module;
(4) and sending the working mode control instruction information to the mode generation module.
(5) And controlling the movement of the fire-fighting gun holder.
The communication module is mainly used for data communication between the full-intelligent fire extinguishing system and a third-party system.
The thermal imager module sends the monitored two-dimensional temperature distribution information of the fire hazard source to the digital signal processing module, and the connection mode of the thermal imager module and the digital signal processing module includes but is not limited to: network cable, wireless network, data bus. After receiving the temperature distribution information, the digital signal processing module performs digital characteristic processing on the two-dimensional temperature distribution information and sends the processed information to the algorithm module 1, and the digital signal processing module is connected with the algorithm module 1 through a data bus; the algorithm module 1 receives the temperature information transmitted by the digital signal processing module, analyzes and judges the fire hazard and the fire occurrence event according to the received temperature information, and simultaneously transmits the analysis and judgment result to the control module, and the algorithm module 1 is connected with the control module through a data bus.
The control module receives the analysis and judgment results of the fire hazard and the fire occurrence event transmitted by the algorithm module 1, and on one hand, the results are transmitted to a third-party system through the communication module; on the other hand, the analysis and judgment result of the algorithm module 2 is called, and the final control decision is made according to the results of the algorithm module 1 and the algorithm module 2. The control module is connected with the communication module through a data bus.
The image acquisition module sends acquired on-site real-time images to the storage module, and the connection mode between the image acquisition module and the storage module comprises but is not limited to a network cable, a wireless network and a data bus; the storage module sends the real-time image information to the algorithm module 2 for analysis and processing so as to judge whether a fire accident occurs; the storage module is connected with the algorithm module 2 through a data bus.
When the algorithm module 2 obtains a fire occurrence event through image analysis processing, on one hand, the algorithm module 2 sends an analysis result of the fire occurrence to the control module; on the other hand, the control module simultaneously calls real-time thermal image temperature data from the algorithm module 1 and makes a final control decision according to results of the algorithm module 1 and the algorithm module 2;
further, the process of the control module making the final control decision according to the results of the algorithm module 1 and the algorithm module 2 is as follows:
(1) if the algorithm module 1 and the control module 2 obtain the consistent analysis result of the fire occurrence event, the control module makes the final decision as the fire occurrence event.
(2) When the algorithm module 1 and the algorithm module 2 analyze the temperature distribution data and the real-time image data at the same time and the obtained event conclusions are different, the control module makes a final decision processing process as follows:
firstly, if the analysis result of the algorithm module 1 is the fire hazard, the algorithm module 2 does not have the capability of analyzing the fire hazard because of the real-time image-based analysis, so that the decision result is based on the analysis result of the algorithm module 1, and the final event decision result is the fire hazard;
if one and only one analysis result of the algorithm module 1 and the algorithm module 2 is a fire event, the algorithm module 2 searches for a sudden change state of the fire event in a rollback mode at a fixed time step, wherein the sudden change state refers to a state sudden change from no fire event to a state with the fire event. If the mutation state point is found, the final event decision result is a fire event; if the sudden change state point is not found, the system decision considers that the fire event analysis result is a false signal, and the control module packages the original analysis result of the algorithm module 1, the original analysis result of the algorithm module 2 and the system decision result data and sends the packaged data to a third-party system through the communication module so as to save records or make a manual intervention decision.
Further, the method for searching the sudden change state of the fire incident in a rolling-back mode at a fixed time step comprises the following steps:
when only one analysis result in the algorithm module 1 and the algorithm module 2 is a fire accident, the system records the time corresponding to the analysis result as a time origin ToAlgorithm module 2 at fixed time step BtAs a unit, call (T) from the memory moduleo+Bt) And (T)o-Bt) The historical images at two moments are analyzed and judged in real time (T) according to the video monitoring datao+Bt) Whether or not an open fire appears at that time, if (T)o+Bt) The naked fire appears at any moment (T)o-Bt) And if no open fire exists at any moment, searching for the mutation state of the fire incident, and finally determining that the system is the fire incident. Otherwise, the final decision result is a non-fire event, and the system enters a normal monitoring state.
When the system decision is the fire hazard, on one hand, the control module sends fire hazard warning information to a third-party system through the communication module; on the other hand, the control module sends an instruction to the mode generation module, the mode generates corresponding working mode information, and the fire-fighting gun pump is controlled to enter a corresponding working mode; and meanwhile, the control module sends a control instruction to control the movement of the fire gun holder, so that the fire gun can extinguish fire at the optimal angle and direction.
When the system decision is a fire event, the control module firstly sends fire event warning information to a third-party system through the communication module; in the second aspect, the control module generates working mode instruction information and sends the working mode instruction information to the mode generation module, and the mode generation module converts the working mode instruction information into corresponding working mode information and controls the fire-fighting gun pump to enter a corresponding working mode; and the control module of the third aspect sends out a control instruction to control the motion of the fire gun holder, so that the fire gun can extinguish fire at the optimal angle and direction.
Has the advantages that:
the fully-intelligent fire extinguishing system can realize fire early warning, find fire intelligent decision, filter false alarm and autonomously decide the optimal fire extinguishing scheme, and has the beneficial effects of all-weather and fully-intelligent handling of the fire hazard at a target point and fire extinguishing handling.
Description of the drawings:
FIG. 1 is a system block diagram of a fully intelligent fire suppression system according to the present invention;
FIG. 2 is a full-color image with two-dimensional temperature distribution information collected by a thermal imager;
FIG. 3 is a flow chart of digital signature processing performed by the digital signal processing module on two-dimensional temperature distribution information;
FIG. 4 is a flow chart of the algorithm module 1 for analyzing and determining the hidden danger and the fire occurrence event of the temperature information;
FIG. 5 is a flow chart of a process for generating corresponding operating mode information by the mode generation module according to the instruction information.
Detailed Description
The fully intelligent fire extinguishing system according to the present invention will be described in detail with reference to the accompanying drawings and specific embodiments.
Referring to fig. 1, the fully intelligent fire extinguishing system of the present invention is composed of the following parts:
the system comprises a thermal imager module (10), a digital signal processing module (20), an algorithm module 1(30), a mode generating module (40), a fire gun pump (50), a cradle head (60), an image acquisition module (70), a storage module (80), an algorithm module 2(90), a control module (100) and a communication module (110).
The thermal imager module (10) is used for monitoring thermal imaging information of the fire-fighting hazard source in real time to obtain two-dimensional temperature distribution information of the fire-fighting hazard source equipment and the material surface, outputting a full-color image in an RGB (red, green and blue) mode by combining the temperature distribution information, as shown in FIG. 2, and sending the two-dimensional temperature distribution information to the digital signal processing module (20). The thermal imager module has the advantages of all-weather monitoring, and no influence of smoke shielding and severe weather.
The digital signal processing module (20) is used for receiving the two-dimensional temperature distribution information of the fire-fighting hazard source equipment and the material surface, which is transmitted from the thermal imager module (10), performing digital characteristic processing on the two-dimensional temperature distribution information and transmitting the processed information to the algorithm module 1(30), so that the algorithm module 1 can directly analyze the temperature information.
The process of the digital signal processing module (20) for performing digital feature processing on the two-dimensional temperature distribution information refers to fig. 3:
s201, storing two-dimensional temperature distribution information to a matrix TP by using description relative to a Cartesian coordinate systemM×N×4Wherein, M and N represent the number of pixels of the two-dimensional temperature distribution full-color image, and dimension 4 represents the information contained in one pixel, including the RGB value and the temperature value corresponding to the RGB value.
Then there is a change in the number of,
wherein (R)ij,Gij,Bij,tij)ijRepresenting the RGB value and the temperature value of the (i, j) th pixel point,i∈[0,(M-1)],j∈[0,(N-1)].
s202 traverse matrix TPM×N×4Extracting pixel information exceeding a temperature threshold value therefrom;
the temperature threshold is manually set, and is marked as omega to indicate that the normal temperature is exceeded, and a limit value which needs extra attention can be set as a minimum threshold value 200 ℃ of the ignition point of a general material in actual operation.
Extraction of TPM×N×4Middle temperature value tijThe elements larger than omega form a new matrix TNm×n×4Then there is
Wherein (R)uv,Guv,Buv,tuv)uvRGB value and temperature value representing the (u, v) th pixel, u belongs to [0, (m-1)],v∈[0,(n-1)]And t isuv>ω.
S203 adopts a fixed window method to carry out over-temperature threshold matrix TNm×n×4Filtering, and obtaining the overtemperature threshold matrix TN 'after filtering'm×n×4To the algorithm module 1.
For TNm×n×4All elements (R) in the matrixuv,Guv,Buv,tuv)uvFiltering is performed sequentially using a fixed window method, that is, a window with a fixed pixel size is adopted, the window size of the fixed pixel should be as small as possible, and in the embodiment, a fixed window with 10 pixels × 10 pixels is adopted to determine the element (R)uv,Guv,Buv,tuv)uvWithin a fixed window, whether there is only (R)uv,Guv,Buv,tuv)uvAn element exceeding the temperature threshold, if indeed only (R)uv,Guv,Buv,tuv)uvIf the temperature exceeds the temperature threshold, the pixel point is judged to be noise data, and the pixel point is filtered; if not only (R) is within the fixed windowuv,Guv,Buv,tuv)uvAnd if the temperature threshold is exceeded, the pixel point is reserved.
Obtaining a final over-temperature threshold matrix recorded as TN 'after filtering treatment by a fixed window method'p×q×4(p is less than or equal to m, q is less than or equal to n) and TN'p×q×4To the algorithm module 1.
The algorithm module 1(30) is stored with a computer program, and is used for receiving the temperature information transmitted by the digital signal processing module (20), analyzing and judging the fire hazard and the fire occurrence event according to the received temperature information, and on the other hand, transmitting the analysis and judgment result to the control module (100).
The algorithm module 1(30) analyzes the temperature information to judge the processing procedures of the fire hazard and the fire occurrence event, and refer to fig. 4:
s301, receiving two-dimensional temperature distribution information transmitted by the digital signal processing module (20), and performing integrated processing in an over-temperature threshold region to obtain an integrated attention object;
the algorithm module 1 receives two-dimensional temperature distribution information transmitted by the digital signal processing module, wherein the two-dimensional temperature distribution information is an over-temperature threshold matrix TN'p×q×4From TN'p×q×4And (4) whether the pixel coordinates of the middle element are continuous or not is carried out to carry out integration processing. Specifically, assuming that the coordinates of the pixel a are (i, j), the coordinates of the pixel B are (i +1, j), the coordinates of the pixel C are (i, j +1), and the coordinates of the pixel D are (i +1, j +1), the pixels A, B, C, D are two-by-two consecutive.
After integration treatment, original overtemperature threshold matrix TN'p×q×4Will be divided into several sub-matrices, denoted as (TN')1...(TN′)wWherein w represents the original overtemperature threshold matrix TN 'after adopting the integration treatment'p×q×4The number of sub-matrices divided, thus resulting in w integrated objects of interest.
S302, the pixel area of the attention object and the increment of the characteristic temperature are calculated, and the fire hazard and the fire occurrence event are judged according to the increment.
(1) For the integrated w objects of interest (TN')1...(TN′)wCalculating the pixel of each object of interest separatelyArea.
The pixel area is used to describe the pixel size of the object of interest, and the pixel area of the object of interest can be used as the object of interest (TN')iSo that the pixel area of the object of interest is equal to the sum of the pixels represented by the elements in the object of interest:
wherein SiA pixel area representing an ith object of interest; p is a radical ofiRepresenting an object of interest (TN')iThe number of rows of middle elements; q. q.siRepresenting an object of interest (TN')iThe number of columns of medium elements.
(2) For the integrated w objects of interest (TN')1...(Tn′)wThe characteristic temperature of each object of interest is calculated separately.
The characteristic temperature is used to characterize the proportion of the highest temperature in a certain object of interest. Object of interest (TN')iThe characteristic temperature calculation method is as follows:
wherein, tfiRepresenting an object of interest (TN')iThe characteristic temperature of (a); p is a radical ofiRepresenting an object of interest (TN')iThe number of rows of middle elements; q. q.siRepresenting an object of interest (TN')iThe number of columns of medium elements; cmiIndicates that t is reachedmiThe number of pixels of (a); t is tmiRepresenting an object of interest (TN')iThe maximum value of the temperature of each pixel in the array.
(3) Calculating the increment of the pixel area and the characteristic temperature, and judging the fire hazard and the fire occurrence event according to the increment, wherein the processing process comprises the following steps:
calculating pixel area growth ga:
Wherein tau isoRepresenting the temperature sampling period of the system thermal image; s'iPixel area, S, representing the current sampling periodiRepresenting the pixel area of the previous sampling period.
② calculating characteristic temperature growth gt:
Wherein, t'fiA characteristic temperature representing a current sampling period; t is tfiRepresenting the characteristic temperature of the previous sampling period.
Analyzing area growth and characteristic temperature growth data of a plurality of continuous sampling periods, and judging the processing process of fire hazard and fire incident:
respectively, representing characteristic temperature growth data for successive r sampling periods.
if it isIllustrating a sharp rise in the characteristic temperature of the object of interest over time;
the mode generating module (40) is used for receiving the instruction information transmitted by the control module (100), generating corresponding working mode information according to the instruction information and then transmitting the working mode information to the fire-fighting gun pump (50).
The processing procedure of the mode generating module (40) for generating the corresponding working mode according to the instruction information refers to fig. 5:
s401, receiving a working mode control instruction transmitted by a control module, and analyzing the control instruction into a PWM (pulse width modulation) signal;
the working mode instruction transmitted by the control module comprises an event decision result and pixel area growth and characteristic temperature growth data of an object of interest in the latest sampling period, and the mode generation module analyzes the working mode instruction into a PWM (pulse width modulation) signal by adopting the following formula after receiving the working mode instruction:
wherein D isjPWM duty cycle representing generating mode of operation
S402, sending the working mode information to the fire fighting gun pump in a PWM signal mode, and controlling the fire fighting gun pump to work according to a specified mode.
The fire-fighting gun pump (50) is used for receiving the working mode information sent by the mode generating module (40) and entering a corresponding working mode so as to control the fire-fighting gun to carry out fire extinguishing treatment more efficiently.
The fire-fighting gun holder (60) is provided with a fire-fighting gun for controlling the spraying angle and direction of the fire-fighting gun.
The image acquisition module (70) is used for acquiring the on-site video monitoring data and storing the image information into the storage module (80).
And the storage module (80) is used for storing the on-site video monitoring data transmitted by the image acquisition module (70).
The algorithm module 2(90) is stored with a computer program, and is used for analyzing the video monitoring data in the storage module (80) in real time so as to automatically judge whether an open fire occurs on the scene and send the judgment result to the control module (100).
The algorithm module 2 analyzes the video monitoring data in real time to automatically judge whether open fire occurs on the site. The method adopts an open fire pattern recognition method based on OpenCV (open source cross-platform computer vision library), adopts an SVM (support vector machine) classifier, a decision tree classifier and an Adaboost (adaptive enhancement) classifier to mix and judge the open fire based on the OpenCV, and can refer to the prior art by the technical personnel in the field, and the detailed steps of the method are not specifically limited.
The control module (100) is mainly used for data transmission and control of the whole fire extinguishing system, and has the following functions:
(1) receiving the analysis and judgment results of the fire hazard and the fire incident transmitted from the algorithm module 1(30), and calling a video analysis result from the algorithm module 2(90) according to the analysis and judgment results to make a final control decision;
(2) receiving the video analysis result transmitted by the algorithm module 2(90), and calling the thermal image temperature information analysis result from the algorithm module 1(30) according to the result to make a final control decision;
(3) reading data from the storage module (80) and the algorithm module 1(30), and transmitting the data to a third-party system through the communication module (110);
(4) and sending the working mode control instruction information to a mode generation module (40).
(5) Controlling the movement of the fire-fighting gun cradle head (60).
The communication module (110) is mainly used for data communication between the fully intelligent fire extinguishing system and a third-party system.
In this embodiment, the thermal imager module sends the monitored two-dimensional temperature distribution information of the fire hazard source to the digital signal processing module, and the connection mode between the thermal imager module and the digital signal processing module includes but is not limited to: network cable, wireless network, data bus. After receiving the temperature distribution information, the digital signal processing module performs digital characteristic processing on the two-dimensional temperature distribution information and sends the processed information to the algorithm module 1, and the digital signal processing module is connected with the algorithm module 1 through a data bus; the algorithm module 1 receives the temperature information transmitted by the digital signal processing module, analyzes and judges the fire hazard and the fire occurrence event according to the received temperature information, and simultaneously transmits the analysis and judgment result to the control module, and the algorithm module 1 is connected with the control module through a data bus.
The control module receives the analysis and judgment results of the fire hazard and the fire occurrence event transmitted by the algorithm module 1, and on one hand, the results are transmitted to a third-party system through the communication module; on the other hand, the analysis and judgment result of the algorithm module 2 is called, and the final control decision is made according to the results of the algorithm module 1 and the algorithm module 2. The control module is connected with the communication module through a data bus.
The image acquisition module sends acquired on-site real-time images to the storage module, and the connection mode between the image acquisition module and the storage module comprises but is not limited to a network cable, a wireless network and a data bus; the storage module sends the real-time image information to the algorithm module 2 for analysis and processing so as to judge whether a fire accident occurs; the storage module is connected with the algorithm module 2 through a data bus.
When the algorithm module 2 obtains a fire occurrence event through image analysis processing, on one hand, the algorithm module 2 sends an analysis result of the fire occurrence to the control module; on the other hand, the control module simultaneously calls real-time thermal image temperature data from the algorithm module 1 and makes a final control decision according to results of the algorithm module 1 and the algorithm module 2;
the process of the control module making the final control decision according to the results of the algorithm module 1 and the algorithm module 2 is as follows:
(1) if the algorithm module 1 and the control module 2 obtain the consistent analysis result of the fire occurrence event, the control module makes the final decision as the fire occurrence event.
(2) When the algorithm module 1 and the algorithm module 2 analyze the temperature distribution data and the real-time image data at the same time and the obtained event conclusions are different, the control module makes a final decision processing process as follows:
firstly, if the analysis result of the algorithm module 1 is the fire hazard, the algorithm module 2 does not have the capability of analyzing the fire hazard because of the real-time image-based analysis, so that the decision result is based on the analysis result of the algorithm module 1, and the final event decision result is the fire hazard;
if one and only one analysis result of the algorithm module 1 and the algorithm module 2 is a fire event, the algorithm module 2 searches for a sudden change state of the fire event in a rollback mode at a fixed time step, wherein the sudden change state refers to a state sudden change from no fire event to a state with the fire event. If the mutation state point is found, the final event decision result is a fire event; if the sudden change state point is not found, the system decision considers that the fire event analysis result is a false signal, and the control module packages the original analysis result of the algorithm module 1, the original analysis result of the algorithm module 2 and the system decision result data and sends the packaged data to a third-party system through the communication module so as to save records or make a manual intervention decision.
The method adopts a rollback mode to search the sudden change state of the fire incident in a fixed time step, and comprises the following processing steps:
when only one analysis result in the algorithm module 1 and the algorithm module 2 is a fire accident, the system records the time corresponding to the analysis result as a time origin ToAlgorithm module 2 at fixed time step BtAs a unit, call (T) from the memory moduleo+Bt) And (T)o-Bt) The historical images at two moments are analyzed and judged in real time (T) according to the video monitoring datao+Bt) Whether or not an open fire appears at that time, if (T)o+Bt) The naked fire appears at any moment (T)o-Bt) And if no open fire exists at any moment, searching for the mutation state of the fire incident, and finally determining that the system is the fire incident. Otherwise, the final decision result is a non-fire event, and the system enters a normal monitoring state.
When the system decision is the fire hazard, on one hand, the control module sends fire hazard warning information to a third-party system through the communication module; on the other hand, the control module sends an instruction to the mode generation module, the mode generates corresponding working mode information, and the fire-fighting gun pump is controlled to enter a corresponding working mode; and meanwhile, the control module sends a control instruction to control the movement of the fire gun holder, so that the fire gun can extinguish fire at the optimal angle and direction.
When the system decision is a fire event, the control module firstly sends fire event warning information to a third-party system through the communication module; in the second aspect, the control module generates working mode instruction information and sends the working mode instruction information to the mode generation module, and the mode generation module converts the working mode instruction information into corresponding working mode information and controls the fire-fighting gun pump to enter a corresponding working mode; and the control module of the third aspect sends out a control instruction to control the motion of the fire gun holder, so that the fire gun can extinguish fire at the optimal angle and direction.
In conclusion, the full-intelligent fire extinguishing system can realize fire early warning, find fire intelligent decision, filter false alarms, analyze fire spread and autonomously decide the optimal fire extinguishing scheme, and has the advantages of all-weather and full-intelligent treatment of the fire hazard at a target point and fire extinguishing treatment.
The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and any equivalent replacement made on the basis of the present invention should be included in the protection scope of the present invention.
Claims (2)
1. A full-intelligent fire extinguishing system processing method is characterized by comprising the following steps: full intelligent fire extinguishing systems includes: the system comprises a thermal imager module, a digital signal processing module, an algorithm module 1, a mode generation module, a fire gun pump, a cradle head, an image acquisition module, a storage module, an algorithm module 2, a control module and a communication module;
the thermal imager module is used for monitoring thermal imaging information of the fire-fighting hazard source in real time to obtain two-dimensional temperature distribution information of the fire-fighting hazard source equipment and the material surface, outputting a full-color image in an RGB (red, green and blue) mode by combining the temperature distribution information and sending the two-dimensional temperature distribution information to the digital signal processing module;
the digital signal processing module is used for receiving the two-dimensional temperature distribution information of the fire-fighting hazard source equipment and the material surface, which is transmitted by the thermal imager module, performing digital characteristic processing on the two-dimensional temperature distribution information and transmitting the processed information to the algorithm module 1;
the algorithm module 1 is used for receiving the temperature information transmitted by the digital signal processing module, analyzing and judging the fire hazard and the fire occurrence event according to the received temperature information, and sending the analysis and judgment result to the control module;
the mode generating module is used for receiving the instruction information transmitted by the control module, generating corresponding working mode information according to the instruction information and then transmitting the working mode information to the fire-fighting gun pump;
the fire-fighting gun pump is used for receiving the working mode information sent by the mode generating module and entering a corresponding working mode so as to control the fire-fighting gun to carry out fire-fighting treatment more efficiently;
the holder is used for controlling the spraying angle and direction of the fire-fighting gun;
the image acquisition module is used for acquiring field video monitoring data and storing image information into the storage module;
the storage module is used for storing the on-site video monitoring data transmitted by the image acquisition module;
the algorithm module 2 is stored with a computer program and is used for analyzing the video monitoring data in the storage module in real time so as to automatically judge whether open fire occurs on the site and send the judgment result to the control module;
the algorithm module 2 analyzes the video monitoring data in real time to automatically judge whether open fire occurs on the site;
the control module is mainly used for data transmission and control of the whole fire extinguishing system;
the communication module is mainly used for data communication between the full-intelligent fire extinguishing system and a third-party system;
the thermal imager module sends the two-dimensional temperature distribution information to the digital signal processing module, the digital signal processing module carries out digital characteristic processing on the two-dimensional temperature distribution information after receiving the temperature distribution information and sends the processed information to the algorithm module 1, and the process of carrying out digital characteristic processing on the two-dimensional temperature distribution information by the digital signal processing module is as follows:
s201, storing two-dimensional temperature distribution information to a matrix TP by using description relative to a Cartesian coordinate systemM×N×4Wherein, M and N represent the pixel number of the two-dimensional temperature distribution full-color image, and dimension 4 represents the information contained in one pixel point, including RGB value and the temperature value corresponding to the RGB value;
wherein the content of the first and second substances,
wherein (R)ij,Gij,Bij,tij)ijRGB value and temperature value representing the (i, j) th pixel, i ∈ [0, (M-1)],j∈[0,(N-1)];
S202 traverse matrix TPM×N×4Extracting pixel information exceeding a temperature threshold value therefrom;
s203 adopts a fixed window method to carry out over-temperature threshold matrix TNm×n×4Filtering, and obtaining the overtemperature threshold matrix TN 'after filtering'm×n×4Sending the data to an algorithm module 1;
for TNm×n×4All elements (R) in the matrixuv,Guv,Buv,tuv)uvFiltering is performed by using a fixed window method, namely, a window with a fixed pixel size is adopted, the window size of the fixed pixel is required to be as small as possible, and a fixed window with 10 pixels multiplied by 10 pixels is adopted to judge the element (R)uv,Guv,Buv,tuv)uvWithin a fixed window, whether there is only (R)uv,Guv,Buv,tuv)uvAn element exceeding the temperature threshold, if indeed only (R)uv,Guv,Buv,tuv)uvIf the temperature exceeds the temperature threshold, the pixel point is judged to be noise data, and the pixel point is filtered; if not only (R) is within the fixed windowuv,Guv,Buv,tuv)uvIf the temperature exceeds the temperature threshold, the pixel point is reserved;
obtaining a final over-temperature threshold matrix recorded as TN 'after filtering treatment by a fixed window method'p×q×4(p is less than or equal to m, q is less than or equal to n) and TN'p×q×4Sending the data to an algorithm module 1;
the digital signal processing module is connected with the algorithm module 1 through a data bus; the algorithm module 1 analyzes and judges the fire hazard and the fire occurrence event according to the received temperature information after receiving the temperature information transmitted by the digital signal processing module, and simultaneously transmits an analysis and judgment result to the control module, wherein the algorithm module 1 is connected with the control module through a data bus;
the algorithm module 1 analyzes the temperature information to judge the processing process of the fire hazard and the fire occurrence event as follows:
s301, receiving two-dimensional temperature distribution information transmitted by the digital signal processing module, and performing integration processing on an over-temperature threshold region to obtain an integrated attention object;
the algorithm module 1 receives two-dimensional temperature distribution information transmitted by the digital signal processing module, wherein the two-dimensional temperature distribution information is an over-temperature threshold matrix TN'p×q×4From TN'p×q×4If the pixel coordinates of the middle element are continuous, the integration process is performed, specifically, if the coordinates of the pixel a are (i, j), the coordinates of the pixel B are (i +1, j), the coordinates of the pixel C are (i, j +1), and the coordinates of the pixel D are (i +1, j +1), the pixels A, B, C, D are continuous two by two;
after integration treatment, original overtemperature threshold matrix TN'p×q×4Will be divided into several sub-matrices, denoted as (TN')1…(TN′)wWherein w represents the original overtemperature threshold matrix TN 'after adopting the integration treatment'p×q×4The number of the sub-matrixes is divided, so that w integrated attention objects are obtained;
s302, calculating the pixel area of the attention object and the increment of the characteristic temperature, and judging the fire hazard and the fire occurrence event according to the increment, wherein the processing process is as follows:
calculating pixel area growth ga:
Wherein tau isoRepresenting the temperature sampling period of the system thermal image; s'iPixel area, S, representing the current sampling periodiRepresents the pixel area of the previous sampling period;
② calculating characteristic temperature growth gt:
Wherein, t'fiA characteristic temperature representing a current sampling period; t is tfiA characteristic temperature representing a previous sampling period;
analyzing area growth and characteristic temperature growth data of a plurality of continuous sampling periods, and judging the processing process of fire hazard and fire incident:
if it isIllustrating a sharp rise in the characteristic temperature of the object of interest over time;
the control module receives the analysis and judgment results of the fire hazard and the fire occurrence event transmitted by the algorithm module 1, and on one hand, the results are transmitted to a third-party system through the communication module; on the other hand, the analysis and judgment result of the algorithm module 2 is called, and a final control decision is made according to the results of the algorithm module 1 and the algorithm module 2; the control module is connected with the communication module through a data bus;
the image acquisition module sends the acquired on-site real-time image to the storage module, and the storage module sends the real-time image information to the algorithm module 2 for analysis and processing so as to judge whether a fire accident occurs; the storage module is connected with the algorithm module 2 through a data bus;
when the algorithm module 2 obtains a fire occurrence event through image analysis processing, on one hand, the algorithm module 2 sends an analysis result of the fire occurrence to the control module; on the other hand, the control module simultaneously calls real-time thermal image temperature data from the algorithm module 1 and makes a final control decision according to results of the algorithm module 1 and the algorithm module 2;
the process of the control module making the final control decision according to the results of the algorithm module 1 and the algorithm module 2 is as follows:
(1) if the algorithm module 1 and the algorithm module 2 obtain the consistent analysis result of the fire occurrence event, the control module makes a final decision to be the fire occurrence event;
(2) when the algorithm module 1 and the algorithm module 2 analyze the temperature distribution data and the real-time image data at the same time and the obtained event conclusions are different, the control module makes a final decision processing process as follows:
firstly, if the analysis result of the algorithm module 1 is the fire hazard, the algorithm module 2 does not have the capability of analyzing the fire hazard because of the real-time image-based analysis, so that the decision result is based on the analysis result of the algorithm module 1, and the final event decision result is the fire hazard;
if one and only one analysis result of the algorithm module 1 and the algorithm module 2 is a fire event, the algorithm module 2 searches for a sudden change state of the fire event in a rollback mode at a fixed time step, wherein the sudden change state refers to a state sudden change from no fire event to a fire event; if the mutation state point is found, the final event decision result is a fire event; if the sudden change state point is not found, the system decision considers that the fire event analysis result is a false signal, and the control module packages the original analysis result of the algorithm module 1, the original analysis result of the algorithm module 2 and the system decision result data and sends the packaged data to a third-party system through the communication module so as to save records or make a manual intervention decision.
2. The fully intelligent fire extinguishing system processing method according to claim 1, wherein a roll-back mode is adopted to search for a sudden change state of a fire event at a fixed time step, and the processing procedure is as follows:
when only one analysis result in the algorithm module 1 and the algorithm module 2 is a fire accident, the system records the time corresponding to the analysis result as a time origin ToAlgorithm module 2 at fixed time step BtAs a unit, call (T) from the memory moduleo+Bt) And (T)o-Bt) The historical images at two moments are analyzed and judged in real time (T) according to the video monitoring datao+Bt) Whether or not an open fire appears at that time, if (T)o+Bt) The naked fire appears at any moment (T)o-Bt) If no open fire exists at all, searching for a sudden change state of the fire event, wherein the final decision result of the system is the fire event, otherwise, the final decision result is a non-fire event, and the system enters a normal monitoring state;
when the system decision is the fire hazard, on one hand, the control module sends fire hazard warning information to a third-party system through the communication module; on the other hand, the control module sends an instruction to the mode generation module, the mode generates corresponding working mode information, and the fire-fighting gun pump is controlled to enter a corresponding working mode; meanwhile, the control module sends out a control instruction to control the movement of the fire gun holder, so that the fire gun can carry out fire extinguishing treatment at the optimal angle and direction;
when the system decision is a fire event, the control module firstly sends fire event warning information to a third-party system through the communication module; in the second aspect, the control module generates working mode instruction information and sends the working mode instruction information to the mode generation module, and the mode generation module converts the working mode instruction information into corresponding working mode information and controls the fire-fighting gun pump to enter a corresponding working mode; and the control module of the third aspect sends out a control instruction to control the motion of the fire gun holder, so that the fire gun can extinguish fire at the optimal angle and direction.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910945263.2A CN110681097B (en) | 2019-09-30 | 2019-09-30 | Full-intelligent fire extinguishing system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910945263.2A CN110681097B (en) | 2019-09-30 | 2019-09-30 | Full-intelligent fire extinguishing system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110681097A CN110681097A (en) | 2020-01-14 |
CN110681097B true CN110681097B (en) | 2021-04-16 |
Family
ID=69111375
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910945263.2A Expired - Fee Related CN110681097B (en) | 2019-09-30 | 2019-09-30 | Full-intelligent fire extinguishing system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110681097B (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103761826A (en) * | 2012-09-10 | 2014-04-30 | 南京恩博科技有限公司 | Identification method of thermal imaging and video double-identification forest fire identification system |
ES2570536T3 (en) * | 2013-05-09 | 2016-05-18 | A M General Contractor S P A | Method of detecting data related to radiated thermal energy in an environment using infrared radiation image processing |
CN106887108A (en) * | 2015-12-16 | 2017-06-23 | 天维尔信息科技股份有限公司 | Early warning interlock method and system based on thermal imaging |
CN107331100A (en) * | 2017-08-01 | 2017-11-07 | 深圳市盛路物联通讯技术有限公司 | A kind of fire alarm method and system based on Internet of Things |
CN107609498A (en) * | 2017-09-01 | 2018-01-19 | 湖州师范学院 | A kind of data processing method of computer supervisory control system |
CN108416968A (en) * | 2018-01-31 | 2018-08-17 | 国家能源投资集团有限责任公司 | Fire alarm method and apparatus |
CN109993941A (en) * | 2019-03-20 | 2019-07-09 | 合肥名德光电科技股份有限公司 | Thermal imaging fire alarm system and its image processing method based on artificial intelligence |
-
2019
- 2019-09-30 CN CN201910945263.2A patent/CN110681097B/en not_active Expired - Fee Related
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103761826A (en) * | 2012-09-10 | 2014-04-30 | 南京恩博科技有限公司 | Identification method of thermal imaging and video double-identification forest fire identification system |
ES2570536T3 (en) * | 2013-05-09 | 2016-05-18 | A M General Contractor S P A | Method of detecting data related to radiated thermal energy in an environment using infrared radiation image processing |
CN106887108A (en) * | 2015-12-16 | 2017-06-23 | 天维尔信息科技股份有限公司 | Early warning interlock method and system based on thermal imaging |
CN107331100A (en) * | 2017-08-01 | 2017-11-07 | 深圳市盛路物联通讯技术有限公司 | A kind of fire alarm method and system based on Internet of Things |
CN107609498A (en) * | 2017-09-01 | 2018-01-19 | 湖州师范学院 | A kind of data processing method of computer supervisory control system |
CN108416968A (en) * | 2018-01-31 | 2018-08-17 | 国家能源投资集团有限责任公司 | Fire alarm method and apparatus |
CN109993941A (en) * | 2019-03-20 | 2019-07-09 | 合肥名德光电科技股份有限公司 | Thermal imaging fire alarm system and its image processing method based on artificial intelligence |
Also Published As
Publication number | Publication date |
---|---|
CN110681097A (en) | 2020-01-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107911653B (en) | Intelligent video monitoring module, system, method and storage medium for residence | |
CN110837822B (en) | Fire-fighting robot injection curve adjusting method and device based on multi-view vision | |
CN103613013B (en) | System and method for monitoring construction safety of tower crane | |
CN102176270A (en) | Safety monitoring and fire alarming integrated system and method | |
CN201897856U (en) | Safety monitoring and fire hazard early-warning integrated system | |
CN112530115B (en) | Electric power operation personnel protection against electric shock scene intelligence supervises integrated equipment | |
CN110021133B (en) | All-weather fire-fighting fire patrol early-warning monitoring system and fire image detection method | |
CN110379111A (en) | A kind of unmanned plane inspection system for forest fire protection | |
CN106778746A (en) | A kind of anti-unmanned plane method of multiple target | |
CN114821406A (en) | Method and system for judging electric power operation field violation behaviors | |
CN110956652A (en) | Early warning method for transformer substation personnel crossing line | |
CN112595730A (en) | Cable breakage identification method and device and computer equipment | |
CN110602453B (en) | Internet of things big data intelligent video security monitoring system | |
CN110681097B (en) | Full-intelligent fire extinguishing system | |
KR20230080522A (en) | Fire monitoring system using artificial intelligence and method thereof | |
CA2394926C (en) | Image data processing | |
CN111145275A (en) | Intelligent automatic control forest fire prevention monitoring system and method | |
CN114534146A (en) | Control method and system for automatically searching for ground based on flame of mobile electric fire-fighting robot | |
CN108520615B (en) | Fire identification system and method based on image | |
CN112597853A (en) | Automatic alarm method and system based on Internet of things | |
KR20070028812A (en) | Method and apparatus for monitoring forest fire using images photographed by camera device | |
CN109872499B (en) | Block on-spot monitoring alarm system based on image recognition | |
CN113343841B (en) | Method and device for determining abnormal condition of power tunnel | |
CN116740874A (en) | Intrusion detection method and related device | |
CN114612771A (en) | Fire source monitoring method and system based on neural network |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210416 Termination date: 20210930 |